RaihanParl

RaihanParl/ai-skill

Command

QA — map Figma UI to data-testid names and pin Figma Comments on each element.

RaihanParl/ai-skill

Cursor rule

Hard default reply style for this user.

RaihanParl/ai-skill

Cursor rule

Evidence-first debugging and validation workflow.

RaihanParl/ai-skill

Cursor rule

Route GitLab MR review requests to gitlab-mr-review.mdc before any other PR workflow.

RaihanParl/ai-skill

Cursor rule

Review GitLab merge requests via glab when user says "mr this" or "pr this".

RaihanParl/ai-skill

Cursor rule

Use Playwright for browser validation in every project.

RaihanParl/ai-skill

Skill Claude CodeCodex

QA workflow that maps interactive Figma UI elements to data-testid names and posts Figma Comments (pins) via the REST API. Invents ids from naming rules when none exist in the codebase yet. Use when the user asks to comment data-testid on a Figma file, runs /figma-testid, or wants QA pins for E2E selectors on a design.

RaihanParl/ai-skill

Agent

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.

RaihanParl/ai-skill

Agent

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.

RaihanParl/ai-skill

Agent

Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

RaihanParl/ai-skill

Agent

Autonomous DevOps agent that monitors Grafana, investigates issues, creates fixes, opens GitLab MRs, and iterates on review feedback — all without human intervention.

RaihanParl/ai-skill

Agent

Interactively installs a validated, resumable /goal workflow into the current workspace.

RaihanParl/ai-skill

Command

Generate a terse caveman-style commit message for staged changes.

RaihanParl/ai-skill

Command

Compress a markdown/text file into caveman format to save tokens.

RaihanParl/ai-skill

Command

Quick reference card for caveman modes, slash commands, and triggers.

RaihanParl/ai-skill

Command

Caveman-style code review — one-line findings with severity.

RaihanParl/ai-skill

Command

Show caveman lifetime token-savings stats.

RaihanParl/ai-skill

Command

Activate caveman compression mode (lite | full | ultra | wenyan | off).

RaihanParl/ai-skill

Command

Design and scaffold a review-gated agent loop with best-practice coaching.

RaihanParl/ai-skill

Command

Interactively install and validate a complete /goal workflow in the current workspace.

RaihanParl/ai-skill

Command

Run the DevOps Watchdog — check Grafana, fix issues, create MR.

RaihanParl/ai-skill

Skill Claude CodeCodex

Use when the user says /breakdown, breakdown tasks, parse OBJECTIVES.md, create issue drafts, or publish-ready tasks for GitHub/GitLab/Jira. Turns objective docs into ranked, dependency-aware, goal-ready plans and asks before any publishing step.

RaihanParl/ai-skill

Skill Claude CodeCodex

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result…

RaihanParl/ai-skill

Skill Claude CodeCodex

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…